Research map / Image generation / Fast diffusion sampling
ViCTr: Vital Consistency Transfer for Pathology Aware Image Synthesis
Onkar Susladkar, Gayatri Deshmukh, Yalcin Tur, Gorkem Durak, Ulas Bagci
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add Stage-1 ATLAS-8k pretraining (ablation) | ViCTr · BTCV generation | FID: 17.33 -> 15.55 | Improved |
| add proposed Tweedie correction to rectified flow (ablation) | ViCTr · BTCV generation | FID: 18.78 -> 15.55 | Improved |
| use proposed rectified flow with Tweedie instead of ReFlow (ablation) | ViCTr · BTCV generation | FID: 20.19 -> 15.55 | Improved |
| use proposed formulation instead of Flow Straight and Fast (ablation) | ViCTr · BTCV generation | FID: 21.37 -> 15.55 | Improved |
| use proposed formulation instead of distribution matching distillation (ablation) | ViCTr · BTCV generation | FID: 22.33 -> 15.55 | Improved |
| add spatial consistency loss to diffusion loss (ablation) | ViCTr · BTCV generation | FID: 18.77 -> 18.21 | Improved |
| add consistency loss to diffusion loss (ablation) | ViCTr · BTCV generation | FID: 18.77 -> 17.02 | Improved |
| combine diffusion, spatial and consistency losses (ablation) | ViCTr · BTCV generation | FID: 18.77 -> 15.55 | Improved |
| raise LoRA rank from 8 to 64 (ablation) | ViCTr · BTCV generation | FID: 18.46 -> 15.55 | Improved |
| raise LoRA rank from 8 to 16 then 32 (ablation) | ViCTr · BTCV generation | FID: 18.46 -> 17.52 -> 16.66 | Improved |
| replace vanilla fine-tuning with ViCTr for Flux | Flux · BTCV generation | FID: 15.52 -> 13.28 | Improved |
| add 30% ViCTr synthetic data to MedSegDiff training | MedSegDiff · CirrMRI600+ | mDSC: 76.92 -> 81.37 | Improved |
Closest papers by meaning
- Knowledge Transfer Scaling Laws for 3D Medical Imaging (NeurIPS 2026 · similarity 0.84)
- STREAM: Stochastic Riemannian Flow Matching with Anisotropic Decoder for Digital Histopathology Image Generation (NeurIPS 2026 · similarity 0.83)
- TumorChain: Interleaved Multimodal Chain-of-Thought Reasoning for Traceable Clinical Tumor Analysis (ICLR 2026 · similarity 0.83)
- Staged and Physics-Grounded Learning Framework with Hyperintensity Prior for Pre-Contrast MRI Synthesis (ICML 2025 · similarity 0.83)
- Arctique: An artificial histopathological dataset unifying realism and controllability for uncertainty quantification (NeurIPS 2024 · similarity 0.82)
- Towards Generalizable Tumor Synthesis (CVPR 2024 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
